LATIDIA · Robótica

¿Hasta dónde puede llegar GPT-6-Astra? Evaluación de capacidades en Zero-Shot Vision-and-Language Navigation

arXiv:2609.20116v2 Tipo de anuncio: reemplazar Resumen: Estudiamos GPT-6-Astra en un sistema de navegación de visión y lenguaje de disparo cero en entornos continuos (VLN-CE), donde interpreta instrucciones, evalúa su entorno

La noticia

arXiv:2609.20116v2 Announce Type: replace Abstract: We study GPT-6-Astra in a zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) system, where it interprets instructions, assesses its surroundings, and proposes actions. The system uses a common observation--decision--execution workflow with direct model API calls, without a packaged agent harness or navigation-specific fine-tuning. In this workflow, each request receives selected observations, execution feedback, and retained progress records. Evaluation covers the complete system, including context management and action control. We evaluate the system on 50 of the 100 R2R-CE val-unseen episodes used by Open-Nav. It achieves a success rate of 52.0\%, an SPL of 48.9\%, and an nDTW of 70.8\%. Our analysis highlights three findings. First,